CONFERENCE: Artificial Intelligence and Statistics (AISTATS) 2010

AISTATS*2010 Call for Papers
Thirteenth International Conference on Artificial Intelligence and Statistics
May 13-15, 2010, Chia Laguna, Sardinia, Italy
http://www.aistats.org

This is the thirteenth conference on Artificial Intelligence and Statistics (AISTATS*2010), an interdisciplinary gathering of researchers at the intersection of computer science, artificial
intelligence, statistics, and related areas.

Since its inception the AISTATS conference has been held every two years in North America. At the 2009 conference, with the support of the EU funded PASCAL II Network of Excellence
(www.pascal-network.org), the decision was made to bring the conference to Europe for the first time. Starting in 2010 AISTATS will be held every year, alternating the venue between Europe and North America.

The Conference Programme will include invited talks, contributed talks, and posters. Contributed talks and posters are selected via a rigorous peer-review process based on 8 page papers. Accepted papers will be published as a special issue in the Journal of Machine Learning Research (JMLR) Workshop and Conference Proceedings Series.

As an innovation for AISTATS*2010, some time at the conference will be set aside for “breaking news” posters submitted on the basis of a one-page abstract. These are reports on ongoing or unpublished projects, projects already published elsewhere, partially developed ideas, negative results etc, and are meant as informal forums to encourage discussion. The review process of these posters will be very light-touch but presentation of these at the Conference will not
lead to publication in the Proceedings.

Since its inception in 1985, the primary goal of this conference has been to broaden research at the interface between artificial intelligence and statistics. Papers and abstracts on all aspects of
this interface are strongly encouraged, including but not limited to:

active learning and experimental design
applications
approximate and exact inference
Bayesian statistics
causality
classification and regression
graphical models
kernel and large margin methods
latent variable models
model selection and structure learning
neural networks
online learning
optimization and search
unsupervised and semi-supervised learning
reinforcement learning and decision making
statistical databases
statistical software
statistical learning theory
structured and relational learning
visualization of datasets

Submission Requirements:

Peer-Reviewed Papers:

Electronic submission of papers is required. Papers may be up to 8 double-column pages in length; formatting and submission information can be found on the AI and Statistics Conference Management page. Submissions will be considered if they are received by 23:59, Friday
November 6th, 2009, Universal Time.

Submitted papers will undergo a rigorous double-blind review process. Acceptance notifications will be emailed by February 13th, and camera-ready final versions (same format) will be due on March 13th, 2010. These papers will be presented at the Conference either as contributed talks or posters, and will be published as a special issue in the JMLR Workshop and Conference Proceedings Series. Papers for talks and posters will be treated equally in publication.

Breaking-news Posters:

Electronic submission of one page double-column abstracts is required. Formatting and submission information can be found on the AI and Statistics Conference Management page. Submissions will be considered if they are received by 23:59, Friday February 26th, 2010, Universal
Time.

Abstracts will be lightly reviewed. Acceptance notifications will be emailed by March 26th. These will be presented as “breaking news” posters at the conference and will not be published.

Programme Chairs:

Yee Whye Teh, University College London, U.K.
Mike Titterington, University of Glasgow, U.K.

General Chair:

Neil Lawrence, University of Manchester, U.K.

Special Issue on “Robot Learning in Practice”, IEEE Robotics and Automation Magazine

CALL FOR PAPERS
Special Issue of the
IEEE Robotics and Automation Magazine
“Robot Learning in Practice”

Guest Editors:

Jun Morimoto (ATR Computational Neuroscience Laboratories, Japan)
Chad Jenkins (Brown University, USA)
Marc Toussaint (TU Berlin, Germany)

Scope:

IEEE Robotics and Automation Magazine (RAM) seeks articles for this special issue, scheduled for publication in June 2010.

There is an increasing interest in machine learning and statistics within the robotics community. At the same time, there has been a growth in the learning community in using robots as motivating
applications for new algorithms and formalisms. Considerable evidence of this exists in the use of learning in high-profile competitions such as RoboCup and the DARPA Challenges, and the growing number of research programs funded by governments around the world.

The proposed special issue is intended to publish contributions on robot learning algorithms with practical applications. Areas of research interest include:

* learning models of robots, task or environments.

* learning hierarchical representations from sensor inputs and motor outputs to task abstractions.

* learning of plans and control policies by imitation and reinforcement learning.

* extraction of low-dimensional task relevant representations for robot learning.

* learning robust policies that work in real environments.

* state estimation algorithms for robot learning.

Submission instructions:

Articles must be around a nominal length of eight pages each. We encourage submission of supplementary material such as experiment videos and source code. For further details see the instruction page:

http://www.ieee-ras.org/ram/for_authors

Submission deadline: October 1st, 2009
Issue date: June 2010

————————————————————————-

Jun Morimoto (point of contact)
Department of Brain Robot Interface
ATR Computational Neuroscience Laboratories
2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan
E-mail : xmorimo (at) atr.jp

Chad Jenkins
Department of Computer Science
Brown University,
115 Waterman St, 4th Floor
Providence, RI, USA 02912-1910
E-mail: cjenkins (at) cs.brown.edu

Marc Toussaint
TU Berlin
Franklinstr. 28/29 FR6-9
10587 Berlin, Germany
E-mail: mtoussai (at) cs.tu-berlin.de

IEEE-RAS TC on Robot Learning web page:
http://www.learning-robots.de/

CfPPP: MLSB-09, SEP 5-6 2009, Ljubljana, Slovenia

MLSB 09: 3rd International Workshop on
Machine Learning in Systems Biology
5-6 September 2009, Ljubljana, Slovenia
http://mlsb09.ijs.si/

3 AUG: Poster abstract submission deadline
17 AUG: Early registration deadline

We kindly invite you to participate and/or present a poster at MLSB-09, the 3rd International Workshop on Machine Learning in Systems Biology. The workshop aims to contribute to the cross-fertilization between the research in machine learning methods and their applications to systems biology. The program of the workshop will include 6 invited talks by renowned researchers and
12 oral presentations of reviewed contributions (see http://mlsb09.ijs.si/program.html for details).
It will also include a poster session: Abstracts for poster presentations can be submitted by 3 AUG 2009.

The Workshop is organized as “core – event” of PASCAL2, Network of Excellence in Pattern Analysis, Statistical Modelling and Computational Learning (http://www.pascal-network.org/) The workshop will take place 5-6 September 2009 at the Jozef Stefan Institute, Ljubljana, Slovenia. It will immediately precede ECML PKDD 2009, taking place 7-11 September 2009 in Bled, Slovenia (Bled is 30 miles from Ljubljana, transport will be organized).

MLCB 2009 “New Problems and Methods in Computational Biology”, Call for Contribution

Call for contributions
New Problems and Methods in Computational Biology
http://www.mlcb.org

A workshop at the Twenty-Third Annual Conference on Neural Information Processing Systems (NIPS 2009) Whistler, BC, Canada, December 11 or 12, 2009.

Deadline for submission of extended abstracts: September 27, 2009,

WORKSHOP DESCRIPTION

The field of computational biology has seen dramatic growth over the past few years, in terms of newly available data, new scientific questions and new challenges for learning and inference. In particular, biological data is often relationally structured and highly diverse, and thus requires combining multiple weak evidence from heterogeneous sources. These sources include sequenced genomes of a variety of organisms, gene expression data from multiple technologies, protein sequence and 3D structural data, protein interaction data, gene ontology and pathway databases, genetic variation data (such as SNPs), and an enormous amount of text data in the biological and medical literature. These new types of scientific and clinical problems require novel
supervised and unsupervised learning approaches that can use these growing resources.

The workshop will host presentations of emerging problems and machine learning techniques in computational biology. We encourage contributions describing either progress on new bioinformatics problems or work on established problems using methods that are substantially different from standard approaches. Kernel methods, graphical models, semi-supervised approaches, feature selection and other techniques applied to relevant bioinformatics problems
would all be appropriate for the workshop.

SUBMISSION INSTRUCTIONS

Researchers interested in contributing should upload an extended abstract of 1-6 pages in PDF format to the MLCB submission web site http://www.easychair.org/conferences/?conf=mlcb2009 by September 27, 2009, 11:59pm (Samoa time).

No special style is required. Authors may use the NIPS style file, but are also free to use other styles as long as they use standard font size (11-12 pt) and margins (1 in).

All submissions will be anonymously peer reviewed and will be evaluated on the basis of their technical content. A strong submission to the workshop typically presents a new learning method
that yields new biological insights, or applies an existing learning method to a new biological problem. However, submissions that improve upon existing methods for solving previously studied problems will also be considered. Examples of research presented in previous years
can be found online at http://www.mlcb.org/nipscompbio/previous/.

Please note that accepted abstracts will be posted online at www.mlcb.org. Authors may submit two versions of their abstract, a longer version for review and a shorter version for posting to the web page. In addition, presentations will be video taped and published online as part of the videolectures.net website supported by Pascal.

The workshop allows submissions of papers that are under review or have been recently published in a conference or a journal. This is done to encourage presentation of mature research projects that are interesting to the community. The authors should clearly state any overlapping published work at time of submission. Authors of accepted abstracts will be invited to submit full length versions of their contributions for publication in a special issue of BMC
Bioinformatics.

ORGANIZERS

Gal Chechik,
Google Research
Tomer Hertz,
Fred Hutchinson Cancer Research Center
William Stafford Noble,
Department of Genome Sciences, University of Washington
Yanjun Qi,
Machine Learning Department, NEC Research
Jean-Philippe Vert,
Mines ParisTech, Institut Curie
Alexander Zien,
LIFE Biosystems

PROGRAM COMMITTEE

Mathieu Blanchette, McGill University
Florence d’Alche-Buc, Université d’Evry-Val d’Essonne, Genopole,
Eleazar Eskin, UC Los Angeles,
Nir Friedman, The Hebrew University of Jerusalem ,
David Heckerman, Microsoft Research ,
Michael I. Jordan, UC Berkeley ,
Christina Leslie, Memorial Sloan-Kettering Cancer Research Center,
Michal Linial, The Hebrew University of Jerusalem ,
Quaid Morris, University of Toronto,
Klaus-Robert Müller, Fraunhofer FIRST ,
Dana Pe’er, Columbia University ,
Uwe Ohler, Duke University ,
Günnar Rätsch, Friedrich Miescher Laboratory of the Max Planck Society,
Alexander Schliep, Rutgers University,
Koji Tsuda, Computational Biology Research Center
Eric Xing, Carnegie-Mellon University ,

PhD opportunities in bioinformatics and biomathematics

Bristol Centre for Systems Biomedicine
Doctoral Training Programme in Bioinformatics and Biomathematics

Bristol Centre for Systems Biomedicine represents an innovative interdisciplinary doctoral training programme offering fully funded 4 (1+3) year studentships, five available in October 2009, five available in 2010. Under the Medical Research Council Capacity Building scheme, these studentships have a £2K pa top up added to the standard stipend of £13K pa, plus tuition fees
and travel/meetings allowance.

High calibre graduates from mathematical, engineering and computationally related disciplines
with a strong interest in developing these skills and applying their abilities to biomedical research, will be trained in a structured and broad programme of relevant short courses, seminars, short (3x3month) projects, and a full PhD project. Programme topics range from population dynamics to the different ‘omics’ (e.g. genomics, proteomics) and pathway and molecular applications. It includes mathematical, statistical and genetic epidemiology, evolutionary, behaviour and mutation theory, evidence synthesis, decision sciences and trials, cell signalling, omics technologies
network inference, DNA, RNA and protein prediction and mathematical modelling in neurophysiological contexts.

In the first core foundation year, students will have a group base in Oakfield House
http://www.bristol.ac.uk/university/maps/google-precinct/index.html.
The programme is led from the Department of Social Medicine with close co-supervisory arrangements with the Departments of Mathematics, Engineering Mathematics, Computer Science and other groups from the medical faculties at the University of Bristol. The host departments all gained very high ratings in RAE2008. BCSBmed is also closely interlinked with five other MRC, Wellcome Trust and EPSRC doctoral training centres in Bristol.

For information about the university, please visit http://www.bristol.ac.uk/ and for a further details: http://www.findaphd.com/

For application forms, please contact the Programme Director, Prof. Ian Day, ian.day (at) bristol.ac.uk.
Please mark your subject line ‘BCSBmed application forms request’ : you will receive an automatic reply.

For information pack or informal enquiries, please contact ian.day (at) bristol.ac.uk, subject line marked ‘BCSBmed information request’.

Further informal enquiries can be directed to C.Campbell (at) bris.ac.uk, subject line marked ‘BCSBmed enquiry’

Open Position : Postdoc in Computational Biology, Cambridge, UK

The genetics lab of Prof. Sir Bruce Ponder and the computational biology lab of Dr. Florian Markowetz at the Cancer Research UK Cambridge Research Institute offer a joint position for a postdoctoral researcher interested in statistical and computational approaches to systems genetics in cancer.

The recent whole-genome scan for breast cancer [1] has identified five novel susceptibility loci. In follow-up work the strongest locus has been narrowed down to two SNPs in the intronic region of the FGFR2 gene [2]. However, a detailed understanding of the disease mechanism is still missing. This project will use a systems biology approach to elucidate the functional roles of FGFR2 and other cancer susceptibility genes. We will integrate diverse genomic data sources (including gene expression, SNPs, copy number variants and others) using statistical network methods [3]. The resulting networks will be used to identify key drivers of disease and their functional mechanisms. The methods developed in breast cancer will also be applied to other cancer types, e.g. lung cancer.

The position bridges between an experimental and a computational lab and is ideal if you are interested in data analysis and method development motivated by close collaborations with experimentalists.

The ideal applicant has a strong background in data analysis and statistical modelling (including knowledge of R or Matlab). Experience in medical or biological research is desireable.

If you are highly motivated to work in an interdisciplinary and very collaborative environment at an internationally recognized research institute, apply by sending your CV to Florian Markowetz at
florian.markowetz (at) cancer.org.uk.

For more information please visit http://www.markowetzlab.org

References

1. DF Easton, …, BAJ Ponder Nature 2007. PMID 17529967
2. KB Meyer, … , BAJ Ponder PLoS Biology 2008. PMID 18462018
3. F Markowetz and R Spang, BMC Bioinf, 2007. PMID 17903286

PhD thesis grant: machine learning and multimodal data

The research labs LIF (http://www.lif.univ-mrs.fr) and LSIS (http://www.lsis.org) together propose a PhD thesis in machine learning applied to multimedia data, within the « Web Multimedia Mining » research group. The thesis will take place in Marseille and Toulon, south-east of France (french riviera), starting in fall 2009. It is granted by the French Minister of Education and Research for 3 years.

The thesis aims at theoretically studying co-training style algorithms to fit multimodal concerns, with application to scaled benchmarks of multimedia data, and the participation to the TRECVID international challenge. The description of the thesis can be found at
http://www.lif.univ-mrs.fr/spip.php?article423.

Supervisors: François Denis, PR (LIF), francois.denis (at) lif.univ-mrs.fr and Hervé Glotin, MCF HDR (LSIS), glotin (at) univ-tln.fr.

Conditions for application: candidates must hold a Master Degree in computer science.

Required skills: fundamental computer science, statistics, machine learning, signal processing, multimedia data representation. Algorithmics and programmation. The candidate must have a master degree in computer science. Matlab and C programming are welcome.

How to apply: please contact the supervisors and send them a Curriculum Vitae with recommandations if any. Deadline for application: july 9th, 2009.

Announcement: Workshop on Structure Adapting Methods, Berlin 6-8 November 2009

Workshop on Structure Adapting Methods
Berlin, 6-8 November 2009
http://www.wias-berlin.de/workshops/sam09/

Registration deadline: October 22, 2009

Scope:

One possible way out of the curse of dimensionality problem is based on one or another structural assumption which allows to reduce the complexity/dimensionality of the model. A number of such structural assumptions is popular in the statistical literature including single- and multiple-index, additive, models, projection pursuit and sparse models, among many others. Knowing the structure allows for applying the classical methods to the reduced models. Unfortunately, the exact structural information is rarely available and the related problem is to extract the structural information from the data as an important preprocessing step.

The aim of this workshop is bringing together leading specialists from the field of adaptive estimation for discussing the new approaches, ideas, challenges and addressing the algorithmic and mathematical aspects of this new and actively developing area of mathematical statistics and machine learning.

Preliminary list of invited speakers:

Peter Bühlmann
Alexander Goldenshluger
Yuri Golubev
Wolfgang Härdle
Joel Horowitz
Anatoly Juditsky
Gerard Kerkyacharian
Oleg Lepski
Mikhail Malioutov
Grigory Milstein
Dominique Picard
Ya’acov Ritov
Alexander Tsybakov

2 Lecturerships in Sheffield, UK

Job Title: Lecturer in Automatic Control & Systems Engineering (2 Posts)
Department: Department of Automatic Control & Systems Engineering

Ref No: R07355

Closing Date: 31st August, 2009

Salary: £36,532 – £43,622 per annum with the potential to progress to £49,096

Summary

Outstanding individuals are sought for two lectureship positions to complement and enhance the multi-disciplinary research portfolio of the Department of Automatic Control and Systems Engineering. Research experience and expertise in (i) Robotics (ii) Aerospace and Transport Systems or (iii) Systems Modelling and Optimisation in Healthcare or in Manufacturing is preferred. Applicants with a strong general background in Systems, Signal Processing and Control are also encouraged to apply. If successful, you will be expected to work closely with relevant department and faculty based research centres. You must have a good first degree and a PhD (or equivalent experience) in a related subject. In addition, you should display an ability and willingness to teach
across the range of taught programmes and to work as part of a team.

http://www.sheffield.ac.uk/jobs/academic.html

Open PhD/Post-doc positions ErcStG MiGraNT project

The MiGraNT project (ERC Starting Grant 240186 : Mining Graphs and Networks: a Theory-based approach) has several (3 to 5) open positions for PhD students and post-doctoral researchers.

The MiGraNT project aims at developing a sound theoretical understanding of mining and learning with graphs, and to exploit this theory to construct effective algorithms for significant real-life applications. Key features of the methodology include the integration of insights from graph theory in data mining and learning approaches, the development of efficient prototype algorithms, and the interdisciplinary collaboration with application domain experts to validate the practical value of the work,

Candidates should have a master in computer science, statistics or mathematics, a PhD in data mining, statistics, graph theory, algorithmics or theoretical computer science, or equivalent. Successful candidates can start on 01/12/2009 or later (negotiable), and funding is possible for up to 5 years.

The host institution of the MiGraNT project is the K.U.Leuven, Belgium, The K.U.Leuven has a strong history of machine learning and data mining research, and offers plenty of opportunities for interactions with researchers of application domains such as medicine, biology, chemistry and computer networks.

Candidates are requested to express their interest by sending email to Jan Ramon (see below) before September 15th, including CV, publication list and names of references.

* Location: Machine learning group (http://www.cs.kuleuven.be/~dtai/ml/), Department of computer science, K.U.Leuven (http://www.kuleuven.be), Leuven, Belgium
* Contact person: Jan Ramon (http://www.cs.kuleuven.be/~janr/ ; Jan (dot) Ramon (at) cs (dot) kuleuven (dot) be)
* More information: http://www.cs.kuleuven.be/~janr/MiGraNT/